{"id":"https://openalex.org/W1967551685","doi":"https://doi.org/10.1117/12.587326","title":"Vision-based speaker location detection","display_name":"Vision-based speaker location detection","publication_year":2005,"publication_date":"2005-03-14","ids":{"openalex":"https://openalex.org/W1967551685","doi":"https://doi.org/10.1117/12.587326","mag":"1967551685"},"language":"en","primary_location":{"id":"doi:10.1117/12.587326","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.587326","pdf_url":null,"source":{"id":"https://openalex.org/S183492911","display_name":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","issn_l":"0277-786X","issn":["0277-786X","1996-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315543","host_organization_name":"SPIE","host_organization_lineage":["https://openalex.org/P4310315543"],"host_organization_lineage_names":["SPIE"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SPIE Proceedings","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079595571","display_name":"Jaehyun Lim","orcid":"https://orcid.org/0000-0001-9723-1873"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jaehyun Lim","raw_affiliation_strings":["Yonsei Univ. (South Korea)"],"affiliations":[{"raw_affiliation_string":"Yonsei Univ. (South Korea)","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111547891","display_name":"Jonggeun Park","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jonggeun Park","raw_affiliation_strings":["Yonsei Univ. (South Korea)"],"affiliations":[{"raw_affiliation_string":"Yonsei Univ. (South Korea)","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100719566","display_name":"Chulhee Lee","orcid":"https://orcid.org/0000-0002-2509-167X"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chulhee Lee","raw_affiliation_strings":["Yonsei Univ. (South Korea)"],"affiliations":[{"raw_affiliation_string":"Yonsei Univ. (South Korea)","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079595571"],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12977572,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"5685","issue":null,"first_page":"904","last_page":"904"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9635999798774719,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9531000256538391,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.819043755531311},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5915043354034424},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49968957901000977},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49180868268013},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4520263373851776},{"id":"https://openalex.org/keywords/videoconferencing","display_name":"Videoconferencing","score":0.4437124729156494},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4423193633556366},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4408143162727356},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2214089035987854},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1289985477924347}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.819043755531311},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5915043354034424},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49968957901000977},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49180868268013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4520263373851776},{"id":"https://openalex.org/C22561748","wikidata":"https://www.wikidata.org/wiki/Q854954","display_name":"Videoconferencing","level":2,"score":0.4437124729156494},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4423193633556366},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4408143162727356},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2214089035987854},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1289985477924347}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1117/12.587326","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.587326","pdf_url":null,"source":{"id":"https://openalex.org/S183492911","display_name":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","issn_l":"0277-786X","issn":["0277-786X","1996-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315543","host_organization_name":"SPIE","host_organization_lineage":["https://openalex.org/P4310315543"],"host_organization_lineage_names":["SPIE"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SPIE Proceedings","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1521049138","https://openalex.org/W1509309911","https://openalex.org/W2144208207","https://openalex.org/W2499802997","https://openalex.org/W1497807607","https://openalex.org/W1813780412","https://openalex.org/W2128773298","https://openalex.org/W2160753975","https://openalex.org/W1940231550","https://openalex.org/W2118860825"],"abstract_inverted_index":{"Generally,":[0],"speaker":[1,20,39,49,66],"location":[2,67],"detection":[3,21,40,50,61],"in":[4,75,92],"video":[5,82,93],"conferencing":[6],"is":[7,14,68],"audio-based.":[8],"However,":[9],"physical":[10],"room":[11,26],"environment":[12],"which":[13,52],"beyond":[15],"the":[16,19,35,85,105],"control":[17],"of":[18,37],"system":[22],"can":[23,33,53],"severely":[24],"change":[25],"acoustics.":[27],"Room":[28],"acoustics":[29],"introduce":[30],"interference":[31],"and":[32,102],"deteriorate":[34],"performance":[36],"audio-based":[38,60],"system.":[41],"In":[42,84],"this":[43],"paper,":[44],"we":[45,88],"propose":[46],"a":[47],"video-based":[48],"method":[51],"be":[54],"used":[55],"independently":[56],"or":[57],"along":[58],"with":[59,110],"systems.":[62],"The":[63],"information":[64,101],"on":[65],"intended":[69],"to":[70,77,81],"create":[71],"3-dimensional":[72],"audio":[73],"reproduction":[74],"order":[76],"provide":[78,113],"more":[79],"reality":[80],"conference.":[83],"proposed":[86],"ethod,":[87],"detect":[89,97],"moving":[90],"lips":[91,98,106],"sequences.":[94],"We":[95],"first":[96],"using":[99],"color":[100],"determine":[103],"whether":[104],"are":[107],"moving.":[108],"Experiments":[109],"real":[111],"videos":[112],"promising":[114],"results.":[115]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}